From Natural Language to Materials Discovery:The Materials Knowledge Navigation Agent

TL;DR

The paper presents MKNA, a language-driven system that automates materials discovery by translating natural language into actions, extracting design principles, and identifying novel high-temperature ceramics.

Contribution

Introduction of MKNA, a novel autonomous system that uses natural language to guide materials discovery, including hypothesis formation and candidate identification.

Findings

Successfully identified high-Debye-temperature ceramics.

Rediscovered known ultra-stiff materials like diamond and SiC.

Proposed new Be-C-rich compounds in unexplored temperature regimes.

Abstract

Accelerating the discovery of high-performance materials remains a central challenge across energy, electronics, and aerospace technologies, where traditional workflows depend heavily on expert intuition and computationally expensive simulations. Here we introduce the Materials Knowledge Navigation Agent (MKNA), a language-driven system that translates natural-language scientific intent into executable actions for database retrieval, property prediction, structure generation, and stability evaluation. Beyond automating tool invocation, MKNA autonomously extracts quantitative thresholds and chemically meaningful design motifs from literature and database evidence, enabling data-grounded hypothesis formation. Applied to the search for high-Debye-temperature ceramics, the agent identifies a literature-supported screening criterion (Theta_D > 800 K), rediscovers canonical ultra-stiff materials such as diamond, SiC, SiN, and BeO, and proposes thermodynamically stable, previously unreported Be-C-rich compounds that populate the sparsely explored 1500-1700 K regime. These results demonstrate that MKNA not only finds stable candidates but also reconstructs interpretable design heuristics, establishing a generalizable platform for autonomous, language-guided materials exploration.